© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 324
    Prev
    Next
    INDEX
    Explanations

    asking for specifics or goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ṓ
    2.08
    ocsát
    1.69
    řich
    1.62
    ‌پ
    1.59
    ־
    1.57
     কর্তৃক
    1.56
    ḗ
    1.56
    ští
    1.55
    átor
    1.55
    ‌های
    1.54
    POSITIVE LOGITS
     haha
    2.07
     alot
    2.04
     nice
    2.01
     hahaha
    2.00
     kinda
    1.90
     hehe
    1.87
    !!!!
    1.86
     :)
    1.81
    !!!
    1.78
     lol
    1.76
    Activations Density 9.483%

    No Known Activations